The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kaedah pemilihan bingkai perwakilan (r-bingkai) optimum menggunakan anggaran fungsi mengikut langkah telah dibangunkan untuk menyediakan pengindeksan automatik untuk sistem ejen pertanyaan video (VQA). Ia menggunakan pengaturcaraan dinamik untuk memilih bingkai-r dan sempadan segmen yang sepadan secara serentak. Eksperimen menunjukkan bahawa ralat penghampiran bagi bingkai-r yang dipilih adalah kurang daripada dua kaedah konvensional. Eksperimen mendapatkan semula menggunakan enjin carian imej berasaskan ciri menunjukkan bahawa kaedah yang dicadangkan adalah lebih teguh dan berkesan daripada dua kaedah konvensional. Kaedah yang dicadangkan telah dilaksanakan dalam sistem VQA dan masa pemprosesan dinilai. Keputusan menunjukkan bahawa masa pemprosesan untuk pengindeksan adalah lebih pendek daripada kaedah konvensional.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Katsunobu FUSHIKIDA, Yoshitsugu HIWATARI, Hideyo WAKI, "A Representative-Video-Frame Selection Method for a Content-Based Video-Query-Agent System" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 6, pp. 1274-1281, June 2000, doi: .
Abstract: An optimum representative-frames (r-frames) selection method using step-wise function approximation has been developed to provide automatic indexing for a video-query-agent (VQA) system. It uses dynamic programming to simultaneously select the r-frames and corresponding segment boundaries. Experiments showed that the approximation error of the selected r-frames was less than that of two conventional methods. Retrieval experiments using a feature-based image-search engine showed that the proposed method is more robust and effective than the two conventional methods. The proposed method was implemented in a VQA system and processing time was evaluated. The results showed that the processing time for indexing was shorter than that of the conventional method.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_6_1274/_p
Salinan
@ARTICLE{e83-d_6_1274,
author={Katsunobu FUSHIKIDA, Yoshitsugu HIWATARI, Hideyo WAKI, },
journal={IEICE TRANSACTIONS on Information},
title={A Representative-Video-Frame Selection Method for a Content-Based Video-Query-Agent System},
year={2000},
volume={E83-D},
number={6},
pages={1274-1281},
abstract={An optimum representative-frames (r-frames) selection method using step-wise function approximation has been developed to provide automatic indexing for a video-query-agent (VQA) system. It uses dynamic programming to simultaneously select the r-frames and corresponding segment boundaries. Experiments showed that the approximation error of the selected r-frames was less than that of two conventional methods. Retrieval experiments using a feature-based image-search engine showed that the proposed method is more robust and effective than the two conventional methods. The proposed method was implemented in a VQA system and processing time was evaluated. The results showed that the processing time for indexing was shorter than that of the conventional method.},
keywords={},
doi={},
ISSN={},
month={June},}
Salinan
TY - JOUR
TI - A Representative-Video-Frame Selection Method for a Content-Based Video-Query-Agent System
T2 - IEICE TRANSACTIONS on Information
SP - 1274
EP - 1281
AU - Katsunobu FUSHIKIDA
AU - Yoshitsugu HIWATARI
AU - Hideyo WAKI
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2000
AB - An optimum representative-frames (r-frames) selection method using step-wise function approximation has been developed to provide automatic indexing for a video-query-agent (VQA) system. It uses dynamic programming to simultaneously select the r-frames and corresponding segment boundaries. Experiments showed that the approximation error of the selected r-frames was less than that of two conventional methods. Retrieval experiments using a feature-based image-search engine showed that the proposed method is more robust and effective than the two conventional methods. The proposed method was implemented in a VQA system and processing time was evaluated. The results showed that the processing time for indexing was shorter than that of the conventional method.
ER -